Inference Software Engineer
Etched · San Jose
Infrastructureonsite$175k–$400k
At a glance
Highlights
- Build hardware for frontier intelligence focused on inference throughput.
- Scale runtime for multi-node inference and robust state management.
- Port state-of-the-art models to a novel custom chip architecture.
What they offer
- Medical, dental, and vision with generous premium coverage
- Housing subsidy for those living within walking distance of office
- Relocation support to San Jose
- Daily lunch and dinner in office
- Wellness benefits for fitness and mental health
- Significant equity
- Unlimited compute budget
Ideal candidate
Systems-minded engineer who loves performance tuning and low-level problem solving across hardware and software. Thrives in-person tackling frontier inference challenges with curiosity and ownership.
Requirements
- Proficiency in C++ or Rust
- Understanding of performance-sensitive or distributed systems like Linux internals, accelerators, compilers, or high-speed interconnects
- Familiarity with PyTorch or JAX
- Experience porting applications to non-standard accelerator hardware
- remote policy
- Fully in-person
Lab profile
About Etched
Building specialized AI chips and systems for frontier inference with best-in-class throughput and latency.
What they build
- Sohu AI inference chip
- AI racks and hardware systems
- Inference software stack
Known for
- Full-stack co-design of chips, racks, software and manufacturing
- Best-in-class throughput and latency for prefill and decode
- Inference-optimized architecture
Key facts
- Backed by hundreds of millions from top-tier investors
Posted · Last seen